microsoft / microsoft/microxcaling
mx.matmul overhead
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 364
- Forks
- 53
- PR merge metrics
- No merged PRs in 30d
Description
Do you have any benchmarks showing where the extra overhead of mx.matmul over a regular matmul is? Is it in the quantization step (calculating scales, rounding, etc.)? If so, do you know if devices with MX support will do this rounding in the hardware itself, and if so, will the overhead become negligible there because of the hardware support?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names mx.matmul but does not identify benchmark files or tests. Start by locating mx.matmul and the regular matmul implementation, then compare their execution costs across available paths. Done means producing reproducible overhead measurements and documenting what the results show about quantization and hardware support.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- performance
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100